© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 31654
    Prev
    Next
    INDEX
    Explanations

    references to the physical form and cultural significance of books

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    InputBorder
    -0.07
    ensi
    -0.06
    aucoup
    -0.06
     Nu
    -0.06
    ecess
    -0.06
    è¦Ĩ
    -0.06
     Slave
    -0.06
    'gc
    -0.06
     MessageBoxButtons
    -0.06
     espos
    -0.06
    POSITIVE LOGITS
     format
    0.07
     physical
    0.07
     presentation
    0.07
     ì±ħ
    0.07
     reading
    0.07
    physical
    0.06
     pageNumber
    0.06
     pageNum
    0.06
     paper
    0.06
    utenberg
    0.06
    Activations Density 0.009%

    No Known Activations